arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.05940math.OCcs.AImath.AP
收藏

从偏微分方程的角度看待生成扩散模型

A PDE Perspective on Generative Diffusion Models

1 Universit\'e Bourgogne Europe, CNRS, Institut de Mathematiques de Bourgogne, 21000 Dijon, France.;2 Friedrich\ -\ Alexander\ -\ Universit\"at Erlangen\ -\ N\"urnberg, Department of Mathematics, Chair for Dynamics, Control, Machine Learning

Kang Liu, Enrique Zuazua

AI总结:

本文从偏微分方程角度研究生成扩散模型,推导了其数学基础,证明了稳定性并提供了时间演化的数学描述,同时揭示了扩散模型在数据流形上的集中特性及生成模型设计的指导原则。

摘要:

基于偏微分方程的方法,本文深入研究了生成扩散模型的数学基础,推导了其核心理论,并证明了模型的稳定性与一致性。通过熵稳定性方法,我们进一步展示了扩散模型在反向时间动态中,对于紧支撑数据分布和广泛初始化方案,数据流形上的集中特性,其集中速率随时间趋于零而呈平方根级。这些结果提供了理论保证,即在精确的分数引导下,扩散轨迹能够返回数据流形并保持模仿保真度。此外,本文还为扩散模型的设计提供了实践指导,包括分数函数构造、损失函数设计和停止时间选择的原理性标准。整体而言,该框架为生成能力与模仿保真度之间的权衡提供了定量理解,实现了严格分析与模型设计在统一数学视角下的桥梁。

英文摘要:

Score-based diffusion models have emerged as a powerful class of generative methods, with successful applications across diverse domains. Despite their empirical success, their mathematical foundations remain only partially understood, particularly regarding the stability and consistency of the stochastic and partial differential equations underlying their dynamics. In this work, we develop a partial differential equation (PDE) framework for score-based diffusion processes associated with the heat flow of a compactly supported data measure. After establishing weak well-posedness on positive-time intervals, we derive a sharp one-sided divergence bound for the score and use it to obtain sharp uniform $L^p$-stability estimates for the generative Fokker--Planck equation. This bound is the Euclidean form of the Li--Yau differential inequality. Through entropy stability methods, we prove that the generated laws converge in the $2$-Wasserstein distance at rate $\sqrt t$ as $t\to0^+$ to a probability measure supported on the data support. This holds for both deterministic and stochastic generation, for positive terminal densities with finite absolute entropy and second moment. In the deterministic case, almost every trajectory converges to a point of the data support; for empirical data, we further obtain a trajectory-wise square-root rate. These results clarify how exact-score dynamics concentrate on the data support without necessarily recovering the data distribution. An explicitly solvable case identifies the limiting weights and their dependence on Gaussian initialization, while a relative-entropy estimate quantifies the effect of score approximation. Together, these findings connect the stability and concentration mechanisms with score learning and early stopping, providing a mathematical perspective on the balance between imitation fidelity and generative diversity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑